Open Textbook
Stanislav Belyaev

Stanislav Belyaev

Engineering Leader at Microsoft

LinkedIn Telegram belyaev.live Talks
> 18
years of experience
2 000+
engineers
700+
graduates
9/10
course rating
Explore the course

Career

Microsoft

Building and scaling engineering teams since 2008 – from startups to enterprises with thousands of developers. At Microsoft, doubled build system productivity for 2,000+ engineers. Previously transformed processes for 600+ IT staff at Tochka Bank, cutting delivery times from weeks to days.

Teaching

Co-author and mentor of the IT Project Manager course at Yandex Practicum – 500+ students over three years. Trainer at Stratoplan with a 9/10 course rating. Three years teaching Project Management in IT at Ural Federal University.

mysummit.school

A platform where managers learn to use AI in practice. Concrete skills: from writing prompts and detecting hallucinations to measuring ROI of AI adoption. Text-based format with interactive assignments – learn at your own pace.

What graduates say

You planted the idea that a project manager is not a taskmaster but part of a team created to find bottlenecks and remove complexity so the team can do their best work. I don't know how my career would have turned out with a different mentor.

Yandex Practicum graduate Project Manager

The 8-week program transformed my career path. Learned to balance features vs. tech debt and position my skills in the job market. Now applying it to release planning.

Stepan Mordvinov QA -> Product Management, SPORTSOFT

Very interesting material for me as a team lead – expanded my understanding of how to communicate with the team at all levels. I immediately started applying everything, especially around tech debt.

Anzhalika Novikava Team Lead

Latest articles

280x Cheaper in Two Years: The AI Economy Has Flipped
9 min

280x Cheaper in Two Years: The AI Economy Has Flipped

In 2023, a single query to GPT-4 cost enough that you had to count carefully. In 2025, the equivalent query became 280 times cheaper. Not 280 percent – 280 times. In two years, the cost of using AI went from a barrier to a rounding error.

Stanford AI Index – the annual report that compiles data on the AI industry from hundreds of sources – flagged this collapse in its 2025 edition. The 2026 report added context: AI investment exploded to $285.9bn, consumers are extracting $172bn of value a year, and data centres are eating electricity at the scale of New York State. The economy flipped – just not the way most people expected.

4 Prompt Engineering Techniques Tested on 7 Models: Workshop Guide
30 min

4 Prompt Engineering Techniques Tested on 7 Models: Workshop Guide

“Analyze this project and give recommendations” – one prompt, seven models, and GPT-5.4 produced 2,231 words of vague advice while Claude Sonnet delivered 11 complimentary phrases like “excellent budget structure.” Rewriting the prompt using a five-element structure brought all seven models down to 346–443 words, and the praise disappeared. Token savings: 41% to 79% depending on the model.

This isn’t theory. This is data from a “Prompt Engineering in Practice” workshop I ran at the IIBA conference. One project brief, four techniques, seven models, 28 runs – and $0.054 total. Cheaper than a vending machine coffee.

99% Quality at 1.4% of the Price: What's Wrong with the AI Model Market
8 min

99% Quality at 1.4% of the Price: What's Wrong with the AI Model Market

Most managers pick an AI model the same way: grab the most expensive one available. The logic makes sense – pricier means better. That’s how enterprise software worked for the last twenty years.

The AI model market in 2026 works differently. The cost per query ranges from $0.0001 to $0.17 – three orders of magnitude. And the actual quality difference between the top ten models? 0.24 points on a five-point scale. Meanwhile, Wharton / GBK Collective reports that a third of corporate AI projects never get past the pilot stage. And Epoch AI shows that only 5.6% of users apply AI in any genuinely deep way.

Maybe the question isn’t which model is best, but whether paying a premium delivers proportionally better results for typical management tasks.

We tested it. The answer was harsher than we expected.

Local LLMs for Managers: What You Can Actually Run at Home
20 min

Local LLMs for Managers: What You Can Actually Run at Home

Anyone who has spent enough time with ChatGPT or Claude eventually asks the question: can I run something similar right on my own laptop – without a subscription, without data leaving the machine, without depending on someone else’s servers?

In 2026, the answer is yes – but the caveats matter more than the answer.

This article is for people already using cloud LLMs who want to understand what local execution actually gives you, what hardware you need, and where expectations break down. No deep technical dive, but concrete numbers.

Course program

Learn how to systematically master AI for management tasks

Course program